Add utility functions and correct tensor dimensions.

Tensor dimensions needed to be reversed since RNN function expect stride 1
in the first dimension.

Remove experimental RNN scripts.

Make inputSize a parameter to the RNN layer and use strings for enum values.

 * add missing cutorch.sychronize() to SpatialConvolution benchmark
 * rename bench to benchSpatial
 * add benchVolumetric

Set weights in __init()

Remove unnecessary input argument to resetIODescriptors

- added new convolution modes
- cleaned up benchVolumetric

Add missing synchronization

test reverted to non-verbose and random optimizer

Return output from RNN:updateOutput and zero cell output.

cuDNN does not set cell output for RNN_RELU so the output was garbage.

Check for nil cx/hx when not training.

Correct self.RNNDesc to self.rnnDesc

1 files changed, 3 insertions, 3 deletions

diff --git a/test/test.lua b/test/test.lua
index 8fcd1b9..ba1b5a1 100644
--- a/test/test.lua
+++ b/test/test.lua
@@ -1444,10 +1444,10 @@ math.randomseed(os.time())
 mytester = torch.Tester()
 mytester:add(cudnntest)
 
--- if torch.random(1,2) == 1 then
+if torch.random(1,2) == 1 then
    cudnn.benchmark = true -- run manual auto-tuner
-   cudnn.verbose = true
--- end
+--   cudnn.verbose = true
+end
 
 
 for i=1,cutorch.getDeviceCount() do